Search

Bone metastasis remains a clinical challenge and is still considered incurable. While nanoparticles-based drug delivery and photothermal therapy (PTT) show promise in treating subcutaneous solid tumor, their therapeutic outcome in treating bone metastasis is limited, due to the inaccessibility of bone metastatic site and the complexity of bone metastasis. Herein, we reported a simple nanoplatform composed of thermo-sensitive liposomes (TSL) and gold nanorods (GNR) to treat bone metastasis through improved chemotherapy combined with GNR-assisted PTT. Lipid combination of TSL was firstly tailored to regulate its stability under physiological condition as well as its sensitivity in responding to PTT-caused mild hyperthermia. The obtained TSL with loaded drug was then combined with GNR to form the nanoplatform through unsophisticated incubation. Cell experiments revealed that upon near-infrared (NIR) irradiation, the nanoplatform effectively inhibited the viability and migration ability of tumor cells through PTT, PTT-triggered thermo-sensitive drug release, and PTT-augmented sensitivity of tumor cells to drug. In a murine model of bone metastasis, the nanoplatform enabled effective delivery of loaded drug and GNR to bone metastatic site for rapid drug release upon local NIR irradiation. Through killing tumor cells and rebalancing the turnover of osteoclasts and osteoblasts, the nanoplatform largely preserved bone structure for pain relief and survival extension. Inspired by the simplicity of nanoplatform acquirement and treatment operation, the strategy of liposomes-based thermo-sensitive drug delivery in combination with GNR-assisted PTT is considered greatly promising in treating bone metastasis.

Constructing personalized and anthropomorphic agents holds significant importance in the simulation of social networks. However, there are still two key problems in existing works: the agent possesses world knowledge that does not belong to its personas, and it cannot eliminate the interference of diverse persona information on current actions, which reduces the personalization and anthropomorphism of the agent. To solve the above problems, we construct the social media agent based on personalized knowledge and dynamic persona information. For personalized knowledge, we add external knowledge sources and match them with the persona information of agents, thereby giving the agent personalized world knowledge. For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action. To make the agent suitable for social media, we design five basic modules for it: persona, planning, action, memory and reflection. To provide an interaction and verification environment for the agent, we build a social media simulation sandbox. In the experimental verification, automatic and human evaluations demonstrated the effectiveness of the agent we constructed.

Audio-text retrieval (ATR), which retrieves a relevant caption given an audio clip (A2T) and vice versa (T2A), has recently attracted much research attention. Existing methods typically aggregate information from each modality into a single vector for matching, but this sacrifices local details and can hardly capture intricate relationships within and between modalities. Furthermore, current ATR datasets lack comprehensive alignment information, and simple binary contrastive learning labels overlook the measurement of fine-grained semantic differences between samples. To counter these challenges, we present a novel ATR framework that comprehensively captures the matching relationships of multimodal information from different perspectives and finer granularities. Specifically, a fine-grained alignment method is introduced, achieving a more detail-oriented matching through a multiscale process from local to global levels to capture meticulous cross-modal relationships. In addition, we pioneer the application of cross-modal similarity consistency, leveraging intra-modal similarity relationships as soft supervision to boost more intricate alignment. Extensive experiments validate the effectiveness of our approach, outperforming previous methods by significant margins of at least 3.9% (T2A) / 6.9% (A2T) R@1 on the AudioCaps dataset and 2.9% (T2A) / 5.4% (A2T) R@1 on the Clotho dataset., Comment: 5 pages, accepted to ICASSP2024

Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature of retraining LLMs, there has been a notable increase in the development of knowledge editing. However, current approaches and evaluations rarely explore the perturbation of editing on neighboring knowledge. This paper studies whether updating new knowledge to LLMs perturbs the neighboring knowledge encapsulated within them. Specifically, we seek to figure out whether appending a new answer into an answer list to a factual question leads to catastrophic forgetting of original correct answers in this list, as well as unintentional inclusion of incorrect answers. A metric of additivity is introduced and a benchmark dubbed as Perturbation Evaluation of Appending Knowledge (PEAK) is constructed to evaluate the degree of perturbation to neighboring knowledge when appending new knowledge. Besides, a plug-and-play framework termed Appending via Preservation and Prevention (APP) is proposed to mitigate the neighboring perturbation by maintaining the integrity of the answer list. Experiments demonstrate the effectiveness of APP coupling with four editing methods on four LLMs. The code and data are available at https://github.com/mjy1111/PEAK., Comment: Accepted by ICML 2024

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. Specifically, a lightweight retrieval evaluator is designed to assess the overall quality of retrieved documents for a query, returning a confidence degree based on which different knowledge retrieval actions can be triggered. Since retrieval from static and limited corpora can only return sub-optimal documents, large-scale web searches are utilized as an extension for augmenting the retrieval results. Besides, a decompose-then-recompose algorithm is designed for retrieved documents to selectively focus on key information and filter out irrelevant information in them. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches. Experiments on four datasets covering short- and long-form generation tasks show that CRAG can significantly improve the performance of RAG-based approaches.

In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This survey aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-based methodologies, as well as comparing their strengths and limitations in evaluating NLG outputs. By discussing unresolved challenges, including bias, robustness, domain-specificity, and unified evaluation, this survey seeks to offer insights to researchers and advocate for fairer and more advanced NLG evaluation techniques., Comment: 19pages

One critical challenge that has emerged is the presence of hallucinations in the output of large language models (LLMs) due to false or outdated knowledge. Since retraining LLMs with updated information is resource-intensive, there has been a growing interest in model editing. However, current model editing methods, while effective in improving editing performance in various scenarios, often overlook potential side effects on the general abilities of LLMs. In this paper, we raise concerns that model editing inherently improves the factuality of the model, but may come at the cost of a significant degradation of these general abilities. Systematically, we analyze side effects by evaluating four popular editing methods on three LLMs across eight representative task categories. Extensive empirical research reveals that current model editing methods are difficult to couple well with LLMs to simultaneously improve the factuality and maintain the general abilities such as reasoning, question answering, etc. Strikingly, the use of a specific method to edit LLaMA-1 (7B) resulted in a drastic performance degradation to nearly 0 on all selected tasks with just a single edit. Therefore, we advocate for more research efforts to minimize the loss of general abilities acquired during LLM pre-training and to ultimately preserve them during model editing., Comment: Add new results on LLaMA-2 (7B)

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training, arising from their extensive parameterization. This challenge is further intensified by the dynamic nature of the world, necessitating frequent updates to LLMs to correct outdated information or integrate new knowledge, thereby ensuring their continued relevance. Note that many applications demand continual model adjustments post-training to address deficiencies or undesirable behaviors. There is an increasing interest in efficient, lightweight methods for on-the-fly model modifications. To this end, recent years have seen a burgeoning in the techniques of knowledge editing for LLMs, which aim to efficiently modify LLMs' behaviors within specific domains while preserving overall performance across various inputs. In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches. Drawing inspiration from educational and cognitive research theories, we propose a unified categorization criterion that classifies knowledge editing methods into three groups: resorting to external knowledge, merging knowledge into the model, and editing intrinsic knowledge. Furthermore, we introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches. Additionally, we provide an in-depth analysis of knowledge location, which can give a deeper understanding of the knowledge structures inherent within LLMs. Finally, we discuss several potential applications of knowledge editing, outlining its broad and impactful implications., Comment: Ongoing work; 52 pages, 282 citations; benchmark is available at https://huggingface.co/datasets/zjunlp/KnowEdit code is available at https://github.com/zjunlp/EasyEdit paper list is available at https://github.com/zjunlp/KnowledgeEditingPapers

Model editing is an emerging field that focuses on updating the knowledge embedded within large language models (LLMs) without extensive retraining. However, current model editing methods significantly compromise the general abilities of LLMs as the number of edits increases, and this trade-off poses a substantial challenge to the continual learning of LLMs. In this paper, we first theoretically analyze that the factor affecting the general abilities in sequential model editing lies in the condition number of the edited matrix. The condition number of a matrix represents its numerical sensitivity, and therefore can be used to indicate the extent to which the original knowledge associations stored in LLMs are perturbed after editing. Subsequently, statistical findings demonstrate that the value of this factor becomes larger as the number of edits increases, thereby exacerbating the deterioration of general abilities. To this end, a framework termed Perturbation Restraint on Upper bouNd for Editing (PRUNE) is proposed, which applies the condition number restraints in sequential editing. These restraints can lower the upper bound on perturbation to edited models, thus preserving the general abilities. Systematically, we conduct experiments employing three popular editing methods on three LLMs across four representative downstream tasks. Evaluation results show that PRUNE can preserve considerable general abilities while maintaining the editing performance effectively in sequential model editing. The code and data are available at https://github.com/mjy1111/PRUNE.

Large language models (LLMs) augmented with retrieval exhibit robust performance and extensive versatility by incorporating external contexts. However, the input length grows linearly in the number of retrieved documents, causing a dramatic increase in latency. In this paper, we propose a novel paradigm named Sparse RAG, which seeks to cut computation costs through sparsity. Specifically, Sparse RAG encodes retrieved documents in parallel, which eliminates latency introduced by long-range attention of retrieved documents. Then, LLMs selectively decode the output by only attending to highly relevant caches auto-regressively, which are chosen via prompting LLMs with special control tokens. It is notable that Sparse RAG combines the assessment of each individual document and the generation of the response into a single process. The designed sparse mechanism in a RAG system can facilitate the reduction of the number of documents loaded during decoding for accelerating the inference of the RAG system. Additionally, filtering out undesirable contexts enhances the model's focus on relevant context, inherently improving its generation quality. Evaluation results of two datasets show that Sparse RAG can strike an optimal balance between generation quality and computational efficiency, demonstrating its generalizability across both short- and long-form generation tasks.

With the rapid advancement of large language models (LLMs) and their remarkable capabilities in handling complex language tasks, an increasing number of studies are employing LLMs as agents to emulate the sequential decision-making processes of humans often represented as Markov decision-making processes (MDPs). The actions within this decision-making framework adhere to specific probability distributions and require iterative sampling. This arouses our curiosity regarding the capacity of LLM agents to comprehend probability distributions, thereby guiding the agent's behavioral decision-making through probabilistic sampling and generating behavioral sequences. To answer the above question, we divide the problem into two main aspects: simulation where the exact probability distribution is known, and generation of sequences where the probability distribution is ambiguous. In the first case, the agent is required to give the type and parameters of the probability distribution through the problem description, and then give the sampling sequence. However, our analysis shows that LLM agents perform poorly in this case, but the sampling success rate can be improved through programming tools. Real-world scenarios often entail unknown probability distributions. Thus, in the second case, we ask the agents to change the activity level in online social networks and analyze the frequency of actions. Ultimately, our analysis shows that LLM agents cannot sample probability distributions even using programming tools. Therefore, careful consideration is still required before directly applying LLM agents as agents to simulate human behavior.

Intent recognition is critical for task-oriented dialogue systems. However, for emerging domains and new services, it is difficult to accurately identify the key intent of a conversation due to time-consuming data annotation and comparatively poor model transferability. Therefore, the automatic induction of dialogue intention is very important for intelligent dialogue systems. This paper presents our solution to Track 2 of Intent Induction from Conversations for Task-Oriented Dialogue at the Eleventh Dialogue System Technology Challenge (DSTC11). The essence of intention clustering lies in distinguishing the representation of different dialogue utterances. The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels. Therefore, we propose a multi-stage coarse-to-fine contrastive learning model training scheme including unsupervised contrastive learning pre-training, supervised contrastive learning pre-training, and fine-tuning with joint contrastive learning and clustering to obtain a better dialogue utterance representation model for the clustering task. In the released DSTC11 Track 2 evaluation results, our proposed system ranked first on both of the two subtasks of this Track., Comment: Ranked 1st on Track 2 at DSTC 11, Accepted by DSTC 11 Workshop

Qiao-Ting Fu,1,* Xiao-Qin Zhong,1,* Mei-Yu Chen,1,* Jia-Yi Gu,2 Jian Zhao,3 De-Hong Yu,4 Fei Tan1,5 1Shanghai Skin Disease Clinical College, The Fifth Clinical Medical College, Anhui Medical University, Shanghai Skin Disease Hospital, Shanghai, 200443, People’s Republic of China; 2Department of Otolaryngology-Head and Neck Surgery, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University, School of Medicine, Shanghai, 200011, People’s Republic of China; 3Department of Oncology-Pathology, Karolinska Institutet, BioClinicum, Karolinska University Hospital Solna, Solna, Sweden; 4Materdicine Lab, School of Life Sciences, Shanghai University, Shanghai, 200444, People’s Republic of China; 5Shanghai Skin Disease Hospital, School of Medicine, Tongji University, Shanghai, 200443, People’s Republic of China*These authors contributed equally to this workCorrespondence: Fei Tan; Dehong Yu, Email tanfeitrue@126.com; dehongyu@126.comBackground and Purpose: Luteolin (LUT), a flavonoid found in various plants, has been reported to have potential therapeutic effects in melanoma. However, poor water solubility and low bioactivity have severely restricted the clinical application of LUT. Based on the high reactive oxygen species (ROS) levels in melanoma cells, we developed nanoparticles encapsulating LUT with the ROS-responsive material poly(propylene sulfide)-poly(ethylene glycol) (PPS-PEG) to enhance the water solubility of LUT, accelerate the release of LUT in melanoma cells, and further enhance its anti-melanoma effect, providing a viable solution for the application of LUT nano-delivery systems in melanoma therapy.Methods: In this study, LUT-loaded nanoparticles were prepared with PPS-PEG and named as LUT-PPS-NPs. Dynamic light scattering (DLS) and transmission electron microscopy (TEM) were applied to determine the size and morphology of LUT-PPS-NPs. In vitro studies were carried out to determine the uptake and mechanism of LUT-PP

Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features have shown their effectiveness and are attracting increasing attention. However, prior work has neither explored the potential of establishing interactions between language-universal features and contextual representations nor incorporated features that can effectively model constituent span attributes and relationships between multiple spans. In this study, a syntax-augmented hierarchical interactive encoder (SHINE) is proposed to transfer cross-lingual IE knowledge. The proposed encoder is capable of interactively capturing complementary information between features and contextual information, to derive language-agnostic representations for various IE tasks. Concretely, a multi-level interaction network is designed to hierarchically interact the complementary information to strengthen domain adaptability. Besides, in addition to the well-studied syntax features of part-of-speech and dependency relation, a new syntax feature of constituency structure is introduced to model the constituent span information which is crucial for IE. Experiments across seven languages on three IE tasks and four benchmarks verify the effectiveness and generalization ability of the proposed method., Comment: 15pages

Modeling multi-party conversations (MPCs) with graph neural networks has been proven effective at capturing complicated and graphical information flows. However, existing methods rely heavily on the necessary addressee labels and can only be applied to an ideal setting where each utterance must be tagged with an addressee label. To study the scarcity of addressee labels which is a common issue in MPCs, we propose MADNet that maximizes addressee deduction expectation in heterogeneous graph neural networks for MPC generation. Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead. To ensure message passing between these conversation fragments, four additional types of latent edges are designed to complete a fully-connected graph. Besides, to optimize the edge-type-dependent message passing for those utterances without addressee labels, an Expectation-Maximization-based method that iteratively generates silver addressee labels (E step), and optimizes the quality of generated responses (M step), is designed. Experimental results on two Ubuntu IRC channel benchmarks show that MADNet outperforms various baseline models on the task of MPC generation, especially under the more common and challenging setting where part of addressee labels are missing., Comment: Accepted by EMNLP 2023. arXiv admin note: text overlap with arXiv:2203.08500

Diffusion models have emerged as the new state-of-the-art family of deep generative models, and their promising potentials for text generation have recently attracted increasing attention. Existing studies mostly adopt a single encoder architecture with partially noising processes for conditional text generation, but its degree of flexibility for conditional modeling is limited. In fact, the encoder-decoder architecture is naturally more flexible for its detachable encoder and decoder modules, which is extensible to multilingual and multimodal generation tasks for conditions and target texts. However, the encoding process of conditional texts lacks the understanding of target texts. To this end, a spiral interaction architecture for encoder-decoder text diffusion (DiffuSIA) is proposed. Concretely, the conditional information from encoder is designed to be captured by the diffusion decoder, while the target information from decoder is designed to be captured by the conditional encoder. These two types of information flow run through multilayer interaction spirally for deep fusion and understanding. DiffuSIA is evaluated on four text generation tasks, including paraphrase, text simplification, question generation, and open-domain dialogue generation. Experimental results show that DiffuSIA achieves competitive performance among previous methods on all four tasks, demonstrating the effectiveness and generalization ability of the proposed method., Comment: Work in Progress

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understanding typically embed interlocutors and utterances into sequential information flows, or utilize only the superficial of inherent graph structures in MPCs. To this end, we present a plug-and-play and lightweight method named graph-induced fine-tuning (GIFT) which can adapt various Transformer-based pre-trained language models (PLMs) for universal MPC understanding. In detail, the full and equivalent connections among utterances in regular Transformer ignore the sparse but distinctive dependency of an utterance on another in MPCs. To distinguish different relationships between utterances, four types of edges are designed to integrate graph-induced signals into attention mechanisms to refine PLMs originally designed for processing sequential texts. We evaluate GIFT by implementing it into three PLMs, and test the performance on three downstream tasks including addressee recognition, speaker identification and response selection. Experimental results show that GIFT can significantly improve the performance of three PLMs on three downstream tasks and two benchmarks with only 4 additional parameters per encoding layer, achieving new state-of-the-art performance on MPC understanding., Comment: Accepted by ACL 2023. arXiv admin note: substantial text overlap with arXiv:2106.01541

This paper describes the system developed by the USTC-NELSLIP team for SemEval-2023 Task 2 Multilingual Complex Named Entity Recognition (MultiCoNER II). A method named Statistical Construction and Dual Adaptation of Gazetteer (SCDAG) is proposed for Multilingual Complex NER. The method first utilizes a statistics-based approach to construct a gazetteer. Secondly, the representations of gazetteer networks and language models are adapted by minimizing the KL divergence between them at both the sentence-level and entity-level. Finally, these two networks are then integrated for supervised named entity recognition (NER) training. The proposed method is applied to XLM-R with a gazetteer built from Wikidata, and shows great generalization ability across different tracks. Experimental results and detailed analysis verify the effectiveness of the proposed method. The official results show that our system ranked 1st on one track (Hindi) in this task., Comment: Winner system (USTC-NELSLIP) of SemEval 2023 MultiCoNER II shared task on Hindi track. arXiv admin note: substantial text overlap with arXiv:2203.03216

Large Language Models (LLMs) have emerged as influential instruments within the realm of natural language processing; nevertheless, their capacity to handle multi-party conversations (MPCs) -- a scenario marked by the presence of multiple interlocutors involved in intricate information exchanges -- remains uncharted. In this paper, we delve into the potential of generative LLMs such as ChatGPT and GPT-4 within the context of MPCs. An empirical analysis is conducted to assess the zero-shot learning capabilities of ChatGPT and GPT-4 by subjecting them to evaluation across three MPC datasets that encompass five representative tasks. The findings reveal that ChatGPT's performance on a number of evaluated MPC tasks leaves much to be desired, whilst GPT-4's results portend a promising future. Additionally, we endeavor to bolster performance through the incorporation of MPC structures, encompassing both speaker and addressee architecture. This study provides an exhaustive evaluation and analysis of applying generative LLMs to MPCs, casting a light upon the conception and creation of increasingly effective and robust MPC agents. Concurrently, this work underscores the challenges implicit in the utilization of LLMs for MPCs, such as deciphering graphical information flows and generating stylistically consistent responses., Comment: Accepted by Findings of EMNLP 2023

Recent studies have demonstrated that large language models (LLMs) store massive factual knowledge within their parameters. But existing LLMs are prone to hallucinate unintended text due to false or outdated knowledge. Since retraining LLMs is resource intensive, there has been a growing interest in the concept of model editing. Despite the emergence of benchmarks and approaches, these unidirectional editing and evaluation have failed to explore the reversal curse. Intuitively, if "The capital of France is" is edited to be a counterfact "London" within a model, then it should be able to naturally reason and recall the reverse fact, i.e., "London is the capital of" followed by "France" instead of "England". In this paper, we study bidirectional language model editing, aiming to provide rigorous model editing evaluation to assess if edited LLMs can recall the editing knowledge bidirectionally. A new evaluation metric of reversibility is introduced, and a benchmark dubbed as Bidirectional Assessment for Knowledge Editing (BAKE) is constructed to evaluate the reversibility of edited models in recalling knowledge in the reverse direction of editing. We surprisingly observe that while current editing methods and LLMs can effectively recall editing facts in the direction of editing, they suffer serious deficiencies when evaluated in the reverse direction. To mitigate the reversal curse, a method named Bidirectionally Inversible Relationship moDeling (BIRD) is proposed. A set of editing objectives that incorporate bidirectional relationships between subject and object into the updated model weights are designed. Experiments show that BIRD improves the performance of four representative LLMs of different sizes via question answering and judgement.

In this paper, we consider optimal pairs trading strategies in terms of static optimality and dynamic optimality under mean–variance criterion. The spread of the entity pairs is assumed to be mean-reverting and follows an Ornstein–Uhlenbeck process. A constrained optimal control problem is considered, and the Lagrange multiplier technique is adopted to transform the primal problem into a family of linear-quadratic optimal control problems that can be solved by the classical dynamic programming principle. Both solutions for static and dynamic optimal pairs trading problems are derived and discussed. We show that the “static and dynamic optimality” is a viable approach to the time-inconsistent control problem. Furthermore, numerical experiments are presented to demonstrate the performance of the optimal pairs trading strategies., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Applied Probability

Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data in target languages. Existing mainstream methods based on the teacher-student distillation framework ignore the rich and complementary information lying in the intermediate layers of pre-trained language models, and domain-invariant information is easily lost during transfer. In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently. Concretely, a multi-channel distillation framework is designed for sufficient information transfer by aggregating multiple distillers as a mixture. Besides, an unsupervised method adopting parallel domain adaptation is proposed to shorten the channels between the teacher and student models to preserve domain-invariant features. Experiments on four datasets across nine languages demonstrate that the proposed method achieves new state-of-the-art performance on zero-shot cross-lingual NER and shows great generalization and compatibility across languages and fields., Comment: 13 pages, 4 figures, accepted by EMNLP2022

Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki pages. However, their ability to access and manipulate the task-specific knowledge is still limited on downstream tasks, as this type of knowledge is usually not well covered in PLMs and is hard to acquire. To address the problem, we propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework. Our model selects knowledge entries from two types of knowledge sources through dense retrieval and then injects them into the input encoding and output decoding stages respectively on the basis of PLMs. With the help of these two types of knowledge, our model can learn what and how to generate. Experiments on two text generation tasks of dialogue generation and question generation, and on two datasets show that our method achieves better performance than various baseline models., Comment: Accepted by Findings of ACL 2022

Recently, various response generation models for two-party conversations have achieved impressive improvements, but less effort has been paid to multi-party conversations (MPCs) which are more practical and complicated. Compared with a two-party conversation where a dialogue context is a sequence of utterances, building a response generation model for MPCs is more challenging, since there exist complicated context structures and the generated responses heavily rely on both interlocutors (i.e., speaker and addressee) and history utterances. To address these challenges, we present HeterMPC, a heterogeneous graph-based neural network for response generation in MPCs which models the semantics of utterances and interlocutors simultaneously with two types of nodes in a graph. Besides, we also design six types of meta relations with node-edge-type-dependent parameters to characterize the heterogeneous interactions within the graph. Through multi-hop updating, HeterMPC can adequately utilize the structural knowledge of conversations for response generation. Experimental results on the Ubuntu Internet Relay Chat (IRC) channel benchmark show that HeterMPC outperforms various baseline models for response generation in MPCs., Comment: Accepted by ACL 2022

As the demand of astronomical observation rising, the telescope systems are becoming more and more complex. Thus, the observatory control software needs to be more intelligent, they have to control each instrument inside the observatory, finish the observation tasks autonomously, and report the information to users if needed. We developed a distributed autonomous observatory control framework named Remote Autonomous Control System 2nd, RACS2 to meet these requirements. The RACS2 framework uses decentralized distributed architecture, instrument control software and system service such as observation control service are implemented as different components. The communication between components is implemented based on a high-performance serialization library and a light-weighted messaging library.The interfaces towards python and Experimental Physics and Industrial Control System (EPICS) are implemented, so the RACS2 framework can communicate with EPICS based device control software and python-based software. Several system components including log, executor, scheduler and other modules are developed to help observation. Observation tasks can be programmed with python language, and the plans are scheduled by the scheduler component to achieve autonomous observation.A set of web service is implemented based on the FastAPI framework, with which user can control and manage the framework remotely.Based on the RACS2 framework, we have implemented the DATs telescope's observation system and the space object observation system.We performed remote autonomous observation and received many data with these systems., Comment: 22 pages, 16 figures

We consider portfolio optimization problems with expected loss constraints under the physical measure (Formula presented.) and the risk neutral measure (Formula presented.), respectively. Using Merton's portfolio as a benchmark portfolio, the optimal terminal wealth of the (Formula presented.) -risk constraint problem can be easily replicated with the standard delta hedging strategy. Motivated by this, we consider the (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint and compare its solution with the true optimal solution of the (Formula presented.) -risk constraint problem. We show the existence and uniqueness of the optimal solution to the (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint, and provide a tractable evaluation method. The (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint is not only easier to implement with standard forwards and puts on a benchmark portfolio than the (Formula presented.) -risk constraint problem, but also easier to solve than either of the (Formula presented.) - or (Formula presented.) -risk constraint problem. The numerical test shows that the difference of the values of the two strategies (the (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint and the optimal strategy solving the (Formula presented.) -risk constraint problem) is reasonably small.

We consider portfolio optimization problems with expected loss constraints under the physical measure (Formula presented.) and the risk neutral measure (Formula presented.), respectively. Using Merton's portfolio as a benchmark portfolio, the optimal terminal wealth of the (Formula presented.) -risk constraint problem can be easily replicated with the standard delta hedging strategy. Motivated by this, we consider the (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint and compare its solution with the true optimal solution of the (Formula presented.) -risk constraint problem. We show the existence and uniqueness of the optimal solution to the (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint, and provide a tractable evaluation method. The (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint is not only easier to implement with standard forwards and puts on a benchmark portfolio than the (Formula presented.) -risk constraint problem, but also easier to solve than either of the (Formula presented.) - or (Formula presented.) -risk constraint problem. The numerical test shows that the difference of the values of the two strategies (the (Formula presented.) -strategy fulfilling the (Formula presented.) -risk constraint and the optimal strategy solving the (Formula presented.) -risk constraint problem) is reasonably small.

Personas are useful for dialogue response prediction. However, the personas used in current studies are pre-defined and hard to obtain before a conversation. To tackle this issue, we study a new task, named Speaker Persona Detection (SPD), which aims to detect speaker personas based on the plain conversational text. In this task, a best-matched persona is searched out from candidates given the conversational text. This is a many-to-many semantic matching task because both contexts and personas in SPD are composed of multiple sentences. The long-term dependency and the dynamic redundancy among these sentences increase the difficulty of this task. We build a dataset for SPD, dubbed as Persona Match on Persona-Chat (PMPC). Furthermore, we evaluate several baseline models and propose utterance-to-profile (U2P) matching networks for this task. The U2P models operate at a fine granularity which treat both contexts and personas as sets of multiple sequences. Then, each sequence pair is scored and an interpretable overall score is obtained for a context-persona pair through aggregation. Evaluation results show that the U2P models outperform their baseline counterparts significantly., Comment: Accepted by EMNLP 2021

Recently, various neural models for multi-party conversation (MPC) have achieved impressive improvements on a variety of tasks such as addressee recognition, speaker identification and response prediction. However, these existing methods on MPC usually represent interlocutors and utterances individually and ignore the inherent complicated structure in MPC which may provide crucial interlocutor and utterance semantics and would enhance the conversation understanding process. To this end, we present MPC-BERT, a pre-trained model for MPC understanding that considers learning who says what to whom in a unified model with several elaborated self-supervised tasks. Particularly, these tasks can be generally categorized into (1) interlocutor structure modeling including reply-to utterance recognition, identical speaker searching and pointer consistency distinction, and (2) utterance semantics modeling including masked shared utterance restoration and shared node detection. We evaluate MPC-BERT on three downstream tasks including addressee recognition, speaker identification and response selection. Experimental results show that MPC-BERT outperforms previous methods by large margins and achieves new state-of-the-art performance on all three downstream tasks at two benchmarks., Comment: Accepted by ACL 2021

Persona can function as the prior knowledge for maintaining the consistency of dialogue systems. Most of previous studies adopted the self persona in dialogue whose response was about to be selected from a set of candidates or directly generated, but few have noticed the role of partner in dialogue. This paper makes an attempt to thoroughly explore the impact of utilizing personas that describe either self or partner speakers on the task of response selection in retrieval-based chatbots. Four persona fusion strategies are designed, which assume personas interact with contexts or responses in different ways. These strategies are implemented into three representative models for response selection, which are based on the Hierarchical Recurrent Encoder (HRE), Interactive Matching Network (IMN) and Bidirectional Encoder Representations from Transformers (BERT) respectively. Empirical studies on the Persona-Chat dataset show that the partner personas neglected in previous studies can improve the accuracy of response selection in the IMN- and BERT-based models. Besides, our BERT-based model implemented with the context-response-aware persona fusion strategy outperforms previous methods by margins larger than 2.7% on original personas and 4.6% on revised personas in terms of hits@1 (top-1 accuracy), achieving a new state-of-the-art performance on the Persona-Chat dataset., Comment: Accepted by SIGIR 2021

Ciguatoxins are natural compounds produced by benthic dinoflagellates Gambierdiscus and Fukuyoa spp., which cause fish intoxication by ciguatera fish poisoning. This study aimed to assess the dietary exposure effects of ciguatoxin P-CTX-1 on the reproductive performance in marine medaka (Oryzias melastigma). Fish which ingested >1.16 pg·day−1 for 21 days exhibited abnormal behaviors including diarrhea, abnormal swimming, loss of appetite and decreased egg production. After 7-day exposure to P-CTX-1 at a dose of 1.93 pg·day−1, significant gender-specific differences in reproductive performance and decreased hatching rate of the offspring were observed. Chemical analysis of P-CTX-1 showed that the P-CTX-1 accumulation rates were 24.1 ± 1.4% in female fish and 9.9 ± 0.4% in male fish, and 0.05 pg·egg−1 was detected. The results illustrate that dietary exposure to P-CTX-1 affected the reproductive performance and survival of offspring, and caused bioaccumulation and maternal transfer of P-CTX-1 in marine medaka. © 2020 Elsevier Ltd

Ciguatoxins are natural compounds produced by benthic dinoflagellates Gambierdiscus and Fukuyoa spp., which cause fish intoxication by ciguatera fish poisoning. This study aimed to assess the dietary exposure effects of ciguatoxin P-CTX-1 on the reproductive performance in marine medaka (Oryzias melastigma). Fish which ingested >1.16 pg·day−1 for 21 days exhibited abnormal behaviors including diarrhea, abnormal swimming, loss of appetite and decreased egg production. After 7-day exposure to P-CTX-1 at a dose of 1.93 pg·day−1, significant gender-specific differences in reproductive performance and decreased hatching rate of the offspring were observed. Chemical analysis of P-CTX-1 showed that the P-CTX-1 accumulation rates were 24.1 ± 1.4% in female fish and 9.9 ± 0.4% in male fish, and 0.05 pg·egg−1 was detected. The results illustrate that dietary exposure to P-CTX-1 affected the reproductive performance and survival of offspring, and caused bioaccumulation and maternal transfer of P-CTX-1 in marine medaka. © 2020 Elsevier Ltd

Ciguatoxins are natural compounds produced by benthic dinoflagellates Gambierdiscus and Fukuyoa spp., which cause fish intoxication by ciguatera fish poisoning. This study aimed to assess the dietary exposure effects of ciguatoxin P-CTX-1 on the reproductive performance in marine medaka (Oryzias melastigma). Fish which ingested >1.16 pg·day−1 for 21 days exhibited abnormal behaviors including diarrhea, abnormal swimming, loss of appetite and decreased egg production. After 7-day exposure to P-CTX-1 at a dose of 1.93 pg·day−1, significant gender-specific differences in reproductive performance and decreased hatching rate of the offspring were observed. Chemical analysis of P-CTX-1 showed that the P-CTX-1 accumulation rates were 24.1 ± 1.4% in female fish and 9.9 ± 0.4% in male fish, and 0.05 pg·egg−1 was detected. The results illustrate that dietary exposure to P-CTX-1 affected the reproductive performance and survival of offspring, and caused bioaccumulation and maternal transfer of P-CTX-1 in marine medaka. © 2020 Elsevier Ltd

The challenges of building knowledge-grounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously. This paper proposes a method named Filtering before Iteratively REferring (FIRE) for this task. In this method, a context filter and a knowledge filter are first built, which derive knowledge-aware context representations and context-aware knowledge representations respectively by global and bidirectional attention. Besides, the entries irrelevant to the conversation are discarded by the knowledge filter. After that, iteratively referring is performed between context and response representations as well as between knowledge and response representations, in order to collect deep matching features for scoring response candidates. Experimental results show that FIRE outperforms previous methods by margins larger than 2.8% and 4.1% on the PERSONA-CHAT dataset with original and revised personas respectively, and margins larger than 3.1% on the CMU_DoG dataset in terms of top-1 accuracy. We also show that FIRE is more interpretable by visualizing the knowledge grounding process., Comment: Accepted by EMNLP 2020 Findings

In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make the model aware of the speaker change information, which is an important and intrinsic property of multi-turn dialogues. Furthermore, a speaker-aware disentanglement strategy is proposed to tackle the entangled dialogues. This strategy selects a small number of most important utterances as the filtered context according to the speakers' information in them. Finally, domain adaptation is performed to incorporate the in-domain knowledge into pre-trained language models. Experiments on five public datasets show that our proposed model outperforms the present models on all metrics by large margins and achieves new state-of-the-art performances for multi-turn response selection., Comment: Accepted by CIKM 2020

Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to. We propose a new model, named Dialogue BERT (DialBERT), which integrates local and global semantics in a single stream of messages to disentangle the conversations that mixed together. We employ BERT to capture the matching information in each utterance pair at the utterance-level, and use a BiLSTM to aggregate and incorporate the context-level information. With only a 3% increase in parameters, a 12% improvement has been attained in comparison to BERT, based on the F1-Score. The model achieves a state-of-the-art result on the a new dataset proposed by IBM and surpasses previous work by a substantial margin.

The NOESIS II challenge, as the Track 2 of the 8th Dialogue System Technology Challenges (DSTC 8), is the extension of DSTC 7. This track incorporates new elements that are vital for the creation of a deployed task-oriented dialogue system. This paper describes our systems that are evaluated on all subtasks under this challenge. We study the problem of employing pre-trained attention-based network for multi-turn dialogue systems. Meanwhile, several adaptation methods are proposed to adapt the pre-trained language models for multi-turn dialogue systems, in order to keep the intrinsic property of dialogue systems. In the released evaluation results of Track 2 of DSTC 8, our proposed models ranked fourth in subtask 1, third in subtask 2, and first in subtask 3 and subtask 4 respectively., Comment: Accepted by AAAI 2020, Workshop on DSTC8

We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8). The DSTC8-Track 4 aims to perform dialogue state tracking (DST) under the zero-shot settings, in which the model needs to generalize on unseen service APIs given a schema definition of these target APIs. Serving as the core for many virtual assistants such as Siri, Alexa, and Google Assistant, the DST keeps track of the user's goal and what happened in the dialogue history, mainly including intent prediction, slot filling, and user state tracking, which tests models' ability of natural language understanding. Recently, the pretrained language models have achieved state-of-the-art results and shown impressive generalization ability on various NLP tasks, which provide a promising way to perform zero-shot learning for language understanding. Based on this, we propose a schema-guided paradigm for zero-shot dialogue state tracking (SGP-DST) by fine-tuning BERT, one of the most popular pretrained language models. The SGP-DST system contains four modules for intent prediction, slot prediction, slot transfer prediction, and user state summarizing respectively. According to the official evaluation results, our SGP-DST (team12) ranked 3rd on the joint goal accuracy (primary evaluation metric for ranking submissions) and 1st on the requsted slots F1 among 25 participant teams., Comment: Present on the DSTC8 Workshop @ AAAI-2020

Task-oriented conversational modeling with unstructured knowledge access, as track 1 of the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to generate response given dialogue history and knowledge access. This challenge can be separated into three subtasks, (1) knowledge-seeking turn detection, (2) knowledge selection, and (3) knowledge-grounded response generation. We use pre-trained language models, ELECTRA and RoBERTa, as our base encoder for different subtasks. For subtask 1 and 2, the coarse-grained information like domain and entity are used to enhance knowledge usage. For subtask 3, we use a latent variable to encode dialog history and selected knowledge better and generate responses combined with copy mechanism. Meanwhile, some useful post-processing strategies are performed on the model's final output to make further knowledge usage in the generation task. As shown in released evaluation results, our proposed system ranks second under objective metrics and ranks fourth under human metrics., Comment: Accepted by AAAI 2021, Workshop on DSTC 9

This paper proposes an utterance-to-utterance interactive matching network (U2U-IMN) for multi-turn response selection in retrieval-based chatbots. Different from previous methods following context-to-response matching or utterance-to-response matching frameworks, this model treats both contexts and responses as sequences of utterances when calculating the matching degrees between them. For a context-response pair, the U2U-IMN model first encodes each utterance separately using recurrent and self-attention layers. Then, a global and bidirectional interaction between the context and the response is conducted using the attention mechanism to collect the matching information between them. The distances between context and response utterances are employed as a prior component when calculating the attention weights. Finally, sentence-level aggregation and context-response-level aggregation are executed in turn to obtain the feature vector for matching degree prediction. Experiments on four public datasets showed that our proposed method outperformed baseline methods on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection., Comment: Accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing. arXiv admin note: substantial text overlap with arXiv:1901.01824

This paper proposes a dually interactive matching network (DIM) for presenting the personalities of dialogue agents in retrieval-based chatbots. This model develops from the interactive matching network (IMN) which models the matching degree between a context composed of multiple utterances and a response candidate. Compared with previous persona fusion approaches which enhance the representation of a context by calculating its similarity with a given persona, the DIM model adopts a dual matching architecture, which performs interactive matching between responses and contexts and between responses and personas respectively for ranking response candidates. Experimental results on PERSONA-CHAT dataset show that the DIM model outperforms its baseline model, i.e., IMN with persona fusion, by a margin of 14.5% and outperforms the current state-of-the-art model by a margin of 27.7% in terms of top-1 accuracy hits@1., Comment: Accepted by EMNLP 2019

We present our work on Track 2 in the Dialog System Technology Challenges 7 (DSTC7). The DSTC7-Track 2 aims to evaluate the response generation of fully data-driven conversation models in knowledge-grounded settings, which provides the contextual-relevant factual texts. The Sequenceto-Sequence models have been widely used for end-to-end generative conversation modelling and achieved impressive results. However, they tend to output dull and repeated responses in previous studies. Our work aims to promote the diversity for end-to-end conversation response generation, which follows a two-stage pipeline: 1) Generate multiple responses. At this stage, two different models are proposed, i.e., a variational generative (VariGen) model and a retrieval based (Retrieval) model. 2) Rank and return the most related response by training a topic coherence discrimination (TCD) model for the ranking process. According to the official evaluation results, our proposed Retrieval and VariGen systems ranked first and second respectively on objective diversity metrics, i.e., Entropy, among all participant systems. And the VariGen system ranked second on NIST and METEOR metrics., Comment: To be present on AAAI19 Workshop---Dialog System Technology Challenges 7 (DSTC7)

In this paper, we propose an interactive matching network (IMN) for the multi-turn response selection task. First, IMN constructs word representations from three aspects to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE), which is capable of encoding sentences hierarchically and generating more descriptive representations by aggregating with an attention mechanism, is designed. Finally, the bidirectional interactions between whole multi-turn contexts and response candidates are calculated to derive the matching information between them. Experiments on four public datasets show that IMN outperforms the baseline models on all metrics, achieving a new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection., Comment: Accepted by CIKM 2019

Zhibing Tang,1,2,* Lin Zhao,1,3,* Zaixing Yang,3 Zhaohui Liu,4 Jia Gu,3 Bing Bai,3 Jinlian Liu,2 Jiaying Xu,3 Huilin Yang1 1Department of Orthopedics, The First Affiliated Hospital of Soochow University, Soochow University, Suzhou, China; 2Department of Orthopaedic Surgery, Suzhou Kowloon Hospital, Shanghai Jiaotong University School of Medicine, Suzhou, China; 3Institute of Quantitative Biology and Medicine, SRMP and RAD-X, Collaborative Innovation Center of Radiation Medicine of Jiangsu Higher Education Institutions, Soochow University, Suzhou, China; 4Department of Anatomy and Histology and Embryology, Basic Medical and Biological Sciences, School of Medicine, Soochow University, Suzhou, China *These authors contributed equally to this work Background: Graphene and its derivative graphene oxide (GO) have been implicated in a wide range of anticancer effects. Purpose: The objective of this study was to systematically evaluate the toxicity and underlying mechanisms of GO on two osteosarcoma (OSA) cancer cell lines, MG-63 and K7M2 cells. Methods: MG-63 and K7M2 cells were treated by GO (0-50 µg/mL) for various time periods. Cell viability was tested by MTT and Live/Dead assays. A ROS Detection Kit based on DHE oxidative reaction was used for ROS detection. An Annexin V-FITC Apoptosis Kit was used for apoptosis detection. Dansylcadaverine (MDC) dyeing was applied for seeking unspecific autophagosomes. Western blot and Immunofluorescence analysis were used for related protein expression and location.Results: K7M2 cells were more sensitive to GO compared with MG-63 cells. The mechanism was attributed to the different extent of the generation of reactive oxygen species (ROS). In K7M2 cells, ROS was easily stimulated and the apoptosis pathway was subsequently activated, accompanied by elevated expression of proapoptosis proteins (such as caspase-3) and decreased expression levels of antiapoptosis proteins (such as Bcl-2). A ROS inhibitor (N-acetylcyste

Zhibing Tang,1,2,* Lin Zhao,1,3,* Zaixing Yang,3 Zhaohui Liu,4 Jia Gu,3 Bing Bai,3 Jinlian Liu,2 Jiaying Xu,3 Huilin Yang1 1Department of Orthopedics, The First Affiliated Hospital of Soochow University, Soochow University, Suzhou, China; 2Department of Orthopaedic Surgery, Suzhou Kowloon Hospital, Shanghai Jiaotong University School of Medicine, Suzhou, China; 3Institute of Quantitative Biology and Medicine, SRMP and RAD-X, Collaborative Innovation Center of Radiation Medicine of Jiangsu Higher Education Institutions, Soochow University, Suzhou, China; 4Department of Anatomy and Histology and Embryology, Basic Medical and Biological Sciences, School of Medicine, Soochow University, Suzhou, China *These authors contributed equally to this work Background: Graphene and its derivative graphene oxide (GO) have been implicated in a wide range of anticancer effects. Purpose: The objective of this study was to systematically evaluate the toxicity and underlying mechanisms of GO on two osteosarcoma (OSA) cancer cell lines, MG-63 and K7M2 cells. Methods: MG-63 and K7M2 cells were treated by GO (0-50 µg/mL) for various time periods. Cell viability was tested by MTT and Live/Dead assays. A ROS Detection Kit based on DHE oxidative reaction was used for ROS detection. An Annexin V-FITC Apoptosis Kit was used for apoptosis detection. Dansylcadaverine (MDC) dyeing was applied for seeking unspecific autophagosomes. Western blot and Immunofluorescence analysis were used for related protein expression and location.Results: K7M2 cells were more sensitive to GO compared with MG-63 cells. The mechanism was attributed to the different extent of the generation of reactive oxygen species (ROS). In K7M2 cells, ROS was easily stimulated and the apoptosis pathway was subsequently activated, accompanied by elevated expression of proapoptosis proteins (such as caspase-3) and decreased expression levels of antiapoptosis proteins (such as Bcl-2). A ROS inhibitor (N-acetylcyste

In this paper, we consider the optimal dividend payment strategy for an insurance company that has two collaborating business lines. The surpluses of the business lines are modeled by diffusion processes. The collaboration between the two business lines permits that money can be transferred from one line to another with or without proportional transaction costs, while money must be transferred from one line to another to help both business lines keep running before simultaneous ruin of the two lines eventually occurs.

This paper presents an end-to-end response selection model for Track 1 of the 7th Dialogue System Technology Challenges (DSTC7). This task focuses on selecting the correct next utterance from a set of candidates given a partial conversation. We propose an end-to-end neural network based on enhanced sequential inference model (ESIM) for this task. Our proposed model differs from the original ESIM model in the following four aspects. First, a new word representation method which combines the general pre-trained word embeddings with those estimated on the task-specific training set is adopted in order to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE) is designed which is capable to encode sentences hierarchically and generate more descriptive representations by aggregation. Third, a new pooling method which combines multi-dimensional pooling and last-state pooling is used instead of the simple combination of max pooling and average pooling in the original ESIM. Last, a modification layer is added before the softmax layer to emphasize the importance of the last utterance in the context for response selection. In the released evaluation results of DSTC7, our proposed method ranked second on the Ubuntu dataset and third on the Advising dataset in subtask 1 of Track 1., Comment: Accepted by AAAI 2019, Workshop on DSTC7

Le Wang, Tiao Wang, Jia-Qi Gu, Hui-Bin Su Department of Anesthesiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, 215000, China Purpose: Sevoflurane is widely used in lung cancer surgery. It is well known that volatile anesthetics have a lung-protective effect in lung cancer surgery. However, the association between the inhibition of cancer cells and miRNAs interference remains unknown. Whether sevoflurane can affect some miRNAs in A549 cells has not been reported. The main aim of the present study was to investigate the effect of 3% sevoflurane on A549 cells and assess whether it regulates A549 cells by interfering with miRNA. Methods: In three percent sevoflurane-pretreated A549 cells, treated for a duration of 30 minutes, the apoptosis rate of A549 cells was evaluated using a flow cytometer. The expression of 6 types of miRNAs associated with non-small cell lung cancer was analyzed by real-time quantitative polymerase chain reaction. Results: An obvious apoptosis-promoting effect was found in A549 cells, which had been treated with 3% sevoflurane. The expression of several miRNAs that regulate apoptosis was significantly changed compared with the control group. Conclusion: Three percent sevoflurane can significantly increase the apoptosis rate of A549 cells, which may reduce the spread of cancer cells caused by operation. Sevoflurane disturbed the expression of the miRNAs that regulate apoptosis. Keywords: sevoflurane, miRNAs, apoptosis

Zhi-Wei Lu,1,2,* Ming-Yu Du,2,* Lu-Xi Qian,1,2 Nan Zhang,2 Jia-Jia Gu,2 Kai Ding,3 Jing Wu,2 Hong-Ming Zhu,2 Xia He,1,2 Li Yin1,2 1The Fourth Clinical School of Nanjing Medical University, Nanjing, Jiangsu, China; 2Department of Radiation Oncology, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing Medical University Affiliated Cancer Hospital, Nanjing, Jiangsu, China; 3Department of Radiation Oncology, Suqian First Hospital, Suqian, Jiangsu, China *These authors contributed equally to this work Background: In recent years, miR-152 has been dysregulated in a variety of tumors and used as a tumor suppressor. Nevertheless, its role in nasopharyngeal carcinoma (NPC) remains unidentified.Materials and methods: Real-time quantitative PCR (polymerase chain reaction) was performed to analyze the expression of miR-152 in NPC cell lines. MiR-152 expression profiles in NPC tissues were obtained from Gene Expression Omnibus (GEO GSE36682). The effect of miR-152 on the invasion and proliferation of NPC cells was determined through cell invasion, wound healing, and cell viability assays. Apoptosis was examined by flow cytometry, and Western blot was performed to measure expression of the target gene. Pyrosequencing was used to detect the methylation level of NPC cells.Results: In this study, miR-152 was downregulated in the NPC tissues and cell lines. When miR-152 was enhanced, the invasion and migration of NPC cells were inhibited. However, miR-152 had no effect on the proliferation of NPC cells. Luciferase reporter gene analysis was performed, and the results showed that DNMT1 (DNA (cytosine-5)-methyltransferase 1) is a direct target of miR-152 in NPC cells. DNMT1 downregulation and miR-152 overexpression both reversed the effects of miR-152 inhibition on the NPC cells. In addition, miR-152 expression increased as a result of the inhibition of the methylation level of miR-152 when DNMT1 expression was downregulated.Conclusion: The overexpression of miR-152